National Centre for Research Methods Phase 2 (2008-11)
Hub: University of Southampton
During this period, the NCRM hub participated in the commissioning of a second phase of research nodes, some of which were continuations of the first phase nodes and some of which were entirely new. The University of Southampton-based hub was renewed and in 2009 Prof Patrick Sturgis (now at the London School of Economics) became the Director. The ReStore repository project continued into a second phase of funding and a further research was added to the hub award. Centre-linked PhD students and collaborative projects continued alongside an expanded training programme and the centre organized the Research Methods Festival 2010. During this period the NCRM nodes were:
ADMIN - Administrative data: methods inference & network
Principal Investigator: Professor Lorraine Dearden
Host Institution: Institute of Education (now University College London)
Legacy Website: Administrative Data - Methods, Inference and Network
Node Publications: Node Publications
ADMIN (Administrative data: methods inference & network) aimed to exploit newly linked administrative and survey longitudinal data to develop and disseminate methodology for making the best use of administrative data and reassessing how best to deal with some of the common problems associated with using survey based longitudinal data.
The research program developed innovative methodological approaches for using administrative data when covariates or responses are missing and using longitudinal survey data when there are problems with measurement error, item non-response and attrition.
Researchers at ADMIN developed innovative methodological approaches to analysing administrative and survey panel data by addressing substantive research questions in the areas of education, economics and social policy. ADMIN also built capacity in using administrative data through training courses, web-based materials, fellowships and studentships as well as by developing an international network of researchers.
BIAS II - Bayesian methods for integrated bias modelling and analysis of multiple data sources in observational studies
Principal Investigator: Professor Nicky Best
Host Institution: Imperial College, London
Legacy Website: BIAS Project
Node Publications: Node Publications
BIAS II (Bayesian methods for integrated bias modelling and analysis of multiple data sources in observational studies) focused on addressing methodological challenges in the modelling of biases and complex structure in observational data, in particular surveys, longitudinal studies and small area data. These methodological challenges include data linkage and methods which combine data from different databases; methods for modelling bias due to survey non-response; longitudinal and spatial analysis, including extension of multilevel models to handle multiple time series and improved methods for handling spatial autocorrelation, scale issues and estimating distributions of small area statistics.
Researchers at BIAS II used Bayesian graphical and hierarchical models as a natural tool for linking many different sub-models and data sources and accounting for important sources of heterogeneity and patterns of correlations in observational data. They applied these models to a range of social science problems covering topics such as crime, voting behaviour, ageing, health and policy evaluation using small area indicators.
BIAS II also ran a programme of training events to help build capacity in advanced quantitative methods – particularly Bayesian methods. Their training programme included specialist workshops, mentoring schemes and visiting fellowships, and they developed freely available software tools to implement many of our methods.
Lancaster-Warwick-Stirling node
Principal Investigator: Professor Brian Francis
Host Institutions: Lancaster University, University of Warwick, University of Stirling
Legacy Website: Lancaster-Warwick Node
Node Publications: Node Publications
Lancaster-Warwick-Stirling node (Developing statistical modelling in the social sciences) aimed to develop and extend statistical methodology and models related to correlated and longitudinal data with substantive applications in criminology, psychology, sociology and education. They also ran a programme of training and capacity building to support researchers in this area.
Researchers at the Lancaster-Warwick-Stirling node
- Developed and extended statistical models for correlated and structured longitudinal data, and associated computational methodologies, building upon existing expertise and experience;
- Used such models to investigate relevant and topical social science problems in criminology, psychology, sociology and education and sought cross-fertilisation in these areas and into other disciplines;
- Developed software and training materials to allow such models to be disseminated to other users;
- Provided a programme of short courses and workshops in the broad area of statistical modelling and advanced courses related to node activity.
LEMMA II - Structures for building, learning, applying and computing statistical models
Principal Investigator: Professor Fiona Steele (now at London School of Economics)
Host Institution: University of Bristol
Legacy Website: Centre for Multilevel Modelling
Node Publications: Node Publications
LEMMA II (Structures for building, learning, applying and computing statistical models) focused on the development of new multilevel modelling methodology to address important social science research questions and capacity building in quantitative social science.
Existing multilevel modelling methodology cannot adequately model dependencies among schools and dependencies between schools and neighbourhoods, and the effects these dependencies have on pupils' learning progress. LEMMA II extended existing methodology to represent these dependencies better which allows more realistic modelling of the effects that school competition and parental selection processes have on pupil’s educational progress.
LEMMA II had three main substantive research areas: school completion, family dynamics and social segregation. Their main areas of statistical methodology development were correlated classifications and missing data in multilevel models. Researchers at LEMMA II implemented the new methodology in a robust user-friendly software which together with an online learning environment and other learning materials and activities formed a programme to build capacity in quantitative social science and facilitate cutting edge social science research
QUIC - Qualitative innovations in CAQDAS
Principal Investigator: Professor Nigel Fielding
Host Institution: University of Surrey; Royal Holloway University of London
Legacy Website: CAQDAS Project
Node Publications: Node Publications
QUIC (Qualitative innovations in CAQDAS) was concerned with the integration and analysis of multiple data sources using CAQDAS software and the dissemination of such techniques through a training and capacity building programme.
QUIC explored qualitative software support for
- Integrating qualitative and quantitative data in mixed methods research;
- The analysis of Access Grid multi-stream visual data;
- The integration of geo-referenced data within qualitative analysis.
QUIC explored the three new areas by applying them to the field of environmental risk. They tested the first two ones in mini-research projects concerning social factors in response to natural environmental risk arising from climate change, and the third one in social environmental risk arising from crime/disorder.
QUIC derived exemplars, teaching datasets, and self-learning materials from each mini-research project and transferred these to its Training and Capacity Building programme.
QUIC was a collaboration between the University of Surrey and Royal Holloway, University of London
Realities - Real life methods for researching relationalities
Principal Investigator: Professor Jennifer Mason
Host Institutions: University of Manchester
Legacy Website: Realities
Node Publications: Node Publications
Realities (Real life methods for researching relationalities) specialised in researching and analysing 'relationalities’ - personal relationships and connections between people. Their particular emphasis was on developing methods that can capture the combination of vital, tangible and intangible dynamics in the way that personal relationships are lived.
Realities took a creative methodological approach that combined traditional methods, both qualitative and quantitative, with new qualitatively-driven approaches.
Realities activities included:
- Two research projects – one focussing on intergenerational dynamics and ageing, and the other on personal associations, affinities and hostilities. Realities used these projects to develop and test their methods for researching relationalities.
- A series of ‘Interdisciplinary dialogue’ events between researchers from across and beyond the social sciences who are using cutting edge methods.
- Training and capacity building activities including one day workshops, shorter “methods workshops”, online resources and a major conference in our final year.
SIMIAN - Simulation innovation
Principal Investigator: Professor Nigel Gilbert
Host Institution: University of Surrey, University of Leicester
Node Publications: Node Publications
SIMIAN (Simulation innovation) developed the methodology and the applicability of simulation in the social sciences. All social science theories try to understand relationships between individuals and larger social patterns, and simulation is a novel technique combining the advantages of statistics (testing models against real data) and qualitative research (recognising the importance of individual interaction for social regularity).
SIMIAN focused on three demonstrator simulations:
- How and when does repeated social interaction lead to co-operative behaviour? Such behaviour may be desirable (care sharing in families) or undesirable (market price fixing) but is found everywhere.
- How do societies handle genuine novelty? What impacts do new technologies have, not just in allowing people to do things faster but in changing the way that society is organised and individuals see the world?
- What are the implications of the fact that societies have normative views (about what should happen) as well as "factual" views (about what did happen) and how do we build theories dealing convincingly with the normative dimensions of social action?
SIMIAN also ran a training and capacity building programme.